Jump to content
AIDA64 Discussion Forum

Recommended Posts

Hello

It's normal that the score of Double-Precision Mandel is higher with GTX 1080 than with RTX 2080 ?

1271757823_gpgpu1080416_34.png.b740e01000264685c55f04179a1e4e86.png  1032174443_gpgpuRTX2080.png.39225699e70d552879eb174fbaf27e91.png

Thanks

Share this post


Link to post
Share on other sites
17 hours ago, tistou77 said:

Hello

It's normal that the score of Double-Precision Mandel is higher with GTX 1080 than with RTX 2080 ?

Thanks

There're a few compromises in the Turing uarch compared to Pascal/Volta that could explain the performance drop.  We however had no chance to dig deeper into Turing just yet.  Once we can get a test sample, we'll analyze the issue.  There may not be room for further optimizations though (on our side), since our OpenCL benchmarks rely heavily on the OpenCL compiler, and the fractal benchmarks are quite simply "too simple" to leave room for any tweakings on our part.  nVIDIA may find some tricks on their side that they can implement in their OpenCL compiler, but I'm not sure how much attention they have about OpenCL benchmarks and optimizing their compiler to better work with such benchmarks :) 

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×